Cancer is one of the leading significant causes of illness and chronic disease worldwide. Skin ca... more Cancer is one of the leading significant causes of illness and chronic disease worldwide. Skin cancer, particularly melanoma, is becoming a severe health problem due to its rising prevalence. The considerable death rate linked with melanoma requires early detection to receive immediate and successful treatment. Lesion detection and classification are more challenging due to many forms of artifacts such as hairs, noise, and irregularity of lesion shape, color, irrelevant features, and textures. In this work, we proposed a deep-learning architecture for classifying multiclass skin cancer and melanoma detection. The proposed architecture consists of four core steps: image preprocessing, feature extraction and fusion, feature selection, and classification. A novel contrast enhancement technique is proposed based on the image luminance information. After that, two pre-trained deep models, DarkNet-53 and DensNet-201, are modified in terms of a residual block at the end and trained through...
Research Journal of Applied Sciences, Engineering and Technology
Requirement elicitation is very difficult process in highly challenging and business based softwa... more Requirement elicitation is very difficult process in highly challenging and business based software as well as in real time software. Common problems associated with these types of software are rapidly changing the requirements and understanding the language of the layman person. In this study, a framework for requirement elicitation by using knowledge based system is proposed, which is very helpful for knowledge documentation, intelligent decision support, self-learning and more specifically it is very helpful for case based reasoning and explanation. Basically in this method requirements are gathered from Artificial Intelligence (AI) expert system from various sources e.g., via interviews, scenarios or use cases. Then, these are converted into structured natural language using ontology and this new problem/case is put forward to Case Based Reasoning (CBR). CBR based on its previous information having similar requirements combines with new case and suggests a proposed solution. Based on this solution a prototype is developed and delivered to customer. The use of case-based reasoning in requirements elicitation process has greatly reduced the burden and saved time of requirement analyst and results in an effective solution for handling complex or vague requirements during the elicitation process.
Tumor detection has been an active research topic in recent years due to the high mortality rate.... more Tumor detection has been an active research topic in recent years due to the high mortality rate. Computer vision (CV) and image processing techniques have recently become popular for detecting tumors in MRI images. The automated detection process is simpler and takes less time than manual processing. In addition, the difference in the expanding shape of brain tumor tissues complicates and complicates tumor detection for clinicians. We proposed a new framework for tumor detection as well as tumor classification into relevant categories in this paper. For tumor segmentation, the proposed framework employs the Particle Swarm Optimization (PSO) algorithm, and for classification, the convolutional neural network (CNN) algorithm. Popular preprocessing techniques such as noise removal, image sharpening, and skull stripping are used at the start of the segmentation process. Then, PSO-based segmentation is applied. In the classification step, two pre-trained CNN models, alexnet and inception-V3, are used and trained using transfer learning. Using a serial approach, features are extracted from both trained models and fused features for final classification. For classification, a variety of machine learning classifiers are used. Average dice values on datasets BRATS-2018 and BRATS-2017 are 98.11 percent and 98.25 percent, respectively, whereas average jaccard values are 96.30 percent and 96.57% (Segmentation Results). The results were extended on the same datasets for classification and achieved 99.0% accuracy, sensitivity of 0.99, specificity of 0.99, and precision of 0.99. Finally, the proposed method is compared to state-of-the-art existing methods and outperforms them.
Industry 4.0 smart manufacturing systems are equipped with sensors, smart machines, and intellige... more Industry 4.0 smart manufacturing systems are equipped with sensors, smart machines, and intelligent robots. The automated in-plant transportation of manufacturing parts through throwing and catching robots is an attempt to accelerate the transportation process and increase productivity by the optimized utilization of in-plant facilities. Such an approach requires intelligent tracking and prediction of the final 3D catching position of thrown objects, while observing their initial flight trajectory in real-time, by catching robot in order to grasp them accurately. Due to non-deterministic nature of such mechanically thrown objects’ flight, accurate prediction of their complete trajectory is only possible if we accurately observe initial trajectory as well as intelligently predict remaining trajectory. The thrown objects in industry can be of any shape but detecting and accurately predicting interception positions of any shape object is an extremely challenging problem that needs to b...
Due to the high demand for mango and being the king of all fruits, it is the need of the hour to ... more Due to the high demand for mango and being the king of all fruits, it is the need of the hour to curb its diseases to fetch high returns. Automatic leaf disease segmentation and identification are still a challenge due to variations in symptoms. Accurate segmentation of the disease is the key prerequisite for any computer-aided system to recognize the diseases, i.e., Anthracnose, apicalnecrosis, etc., of a mango plant leaf. To solve this issue, we proposed a CNN based Fully-convolutional-network (FrCNnet) model for the segmentation of the diseased part of the mango leaf. The proposed FrCNnet directly learns the features of each pixel of the input data after applying some preprocessing techniques. We evaluated the proposed FrCNnet on the real-time dataset provided by the mango research institute, Multan, Pakistan. To evaluate the proposed model results, we compared the segmentation performance with the available state-of-the-art models, i.e., Vgg16, Vgg-19, and Unet. Furthermore, the proposed model's segmentation accuracy is 99.2% with a false negative rate (FNR) of 0.8%, which is much higher than the other models. We have concluded that by using a FrCNnet, the input image could learn better features that are more prominent and much specific, resulting in an improved and better segmentation performance and diseases' identification. Accordingly, an automated approach helps pathologists and mango growers detect and identify those diseases.
Mango fruit is in high demand. So, the timely control of mango plant diseases is necessary to gai... more Mango fruit is in high demand. So, the timely control of mango plant diseases is necessary to gain high returns. Automated recognition of mango plant leaf diseases is still a challenge as manual disease detection is not a feasible choice in this computerized era due to its high cost and the non-availability of mango experts and the variations in the symptoms. Amongst all the challenges, the segmentation of diseased parts is a big issue, being the pre-requisite for correct recognition and identification. For this purpose, a novel segmentation approach is proposed in this study to segment the diseased part by considering the vein pattern of the leaf. This leaf vein-seg approach segments the vein pattern of the leaf. Afterward, features are extracted and fused using canonical correlation analysis (CCA)-based fusion. As a final identification step, a cubic support vector machine (SVM) is implemented to validate the results. The highest accuracy achieved by this proposed model is 95.5%, ...
White blood cells, WBCs for short, are an essential component of the human immune system. These c... more White blood cells, WBCs for short, are an essential component of the human immune system. These cells are our body's first line of defense against infections and diseases caused by bacteria, viruses, and fungi, as well as abnormal and external substances that may enter the bloodstream. A wrong WBC count can signify dangerous viral infections, autoimmune disorders, cancer, sarcoidosis, aplastic anemia, leukemia, tuberculosis, etc. A lot of these diseases and disorders can be extremely painful and often result in death. Leukemia is among the more common types of blood cancer and when left undetected leads to death. An early diagnosis is necessary which is possible by looking at the shapes and determining the numbers of young and immature WBCs to see if they are normal or not. Performing this task manually is a cumbersome, expensive, and time-consuming process for hematologists, and therefore computer-aided systems have been developed to help with this problem. This paper proposes ...
Due to the rapid growth in artificial intelligence (AI) and deep learning (DL) approaches, the se... more Due to the rapid growth in artificial intelligence (AI) and deep learning (DL) approaches, the security and robustness of the deployed algorithms need to be guaranteed. The security susceptibility of the DL algorithms to adversarial examples has been widely acknowledged. The artificially created examples will lead to different instances negatively identified by the DL models that are humanly considered benign. Practical application in actual physical scenarios with adversarial threats shows their features. Thus, adversarial attacks and defense, including machine learning and its reliability, have drawn growing interest and, in recent years, has been a hot topic of research. We introduce a framework that provides a defensive model against the adversarial speckle-noise attack, the adversarial training, and a feature fusion strategy, which preserves the classification with correct labelling. We evaluate and analyze the adversarial attacks and defenses on the retinal fundus images for t...
Documents are stored in a digital form across several organizations. Printing this amount of data... more Documents are stored in a digital form across several organizations. Printing this amount of data and placing it into folders instead of storing digitally is against the practical, economical, and ecological perspective. An efficient way of retrieving data from digitally stored documents is also required. This article presents a real-time supervised learning technique for document classification based on deep convolutional neural network (DCNN), which aims to reduce the impact of adverse document image issues such as signatures, marks, logo, and handwritten notes. The proposed technique’s major steps include data augmentation, feature extraction using pre-trained neural network models, feature fusion, and feature selection. We propose a novel data augmentation technique, which normalizes the imbalanced dataset using the secondary dataset RVL-CDIP. The DCNN features are extracted using the VGG19 and AlexNet networks. The extracted features are fused, and the fused feature vector is o...
Provocative heart disease is related to ventricular arrhythmias (VA). Ventricular tachyarrhythmia... more Provocative heart disease is related to ventricular arrhythmias (VA). Ventricular tachyarrhythmia is an irregular and fast heart rhythm that emerges from inappropriate electrical impulses in the ventricles of the heart. Different types of arrhythmias are associated with different patterns, which can be identified. An electrocardiogram (ECG) is the major analytical tool used to interpret and record ECG signals. ECG signals are nonlinear and difficult to interpret and analyze. We propose a new deep learning approach for the detection of VA. Initially, the ECG signals are transformed into images that have not been done before. Later, these images are normalized and utilized to train the AlexNet, VGG-16 and Inception-v3 deep learning models. Transfer learning is performed to train a model and extract the deep features from different output layers. After that, the features are fused by a concatenation approach, and the best features are selected using a heuristic entropy calculation appr...
As the number of internet users increases so does the number of malicious attacks using malware. ... more As the number of internet users increases so does the number of malicious attacks using malware. The detection of malicious code is becoming critical, and the existing approaches need to be improved. Here, we propose a feature fusion method to combine the features extracted from pre-trained AlexNet and Inception-v3 deep neural networks with features attained using segmentation-based fractal texture analysis (SFTA) of images representing the malware code. In this work, we use distinctive pre-trained models (AlexNet and Inception-V3) for feature extraction. The purpose of deep convolutional neural network (CNN) feature extraction from two models is to improve the malware classifier accuracy, because both models have characteristics and qualities to extract different features. This technique produces a fusion of features to build a multimodal representation of malicious code that can be used to classify the grayscale images, separating the malware into 25 malware classes. The features ...
Feature transformation and key-point identification is the solution to many local feature descrip... more Feature transformation and key-point identification is the solution to many local feature descriptors. One among such descriptor is the Scale Invariant Feature Transform (SIFT). A small effort has been made for designing a hexagonal sampled SIFT feature descriptor with its applicability in face recognition tasks. Instead of using SIFT on square image coordinates, the proposed work makes use of hexagonal converted image pixels and processing is applied on hexagonal coordinate system. The reason of using the hexagonal image coordinates is that it gives sharp edge response and highlights low contrast regions on the face. This characteristic allows SIFT descriptor to mark distinctive facial features, which were previously discarded by original SIFT descriptor. Furthermore, Fisher Canonical Correlation Analysis based discriminate procedure is outlined to give a more precise classification results. Experiments performed on renowned datasets revealed better performances in terms of feature extraction in robust conditions.
Face recognition is one of a complex biometrics in the field of pattern recognition due to the co... more Face recognition is one of a complex biometrics in the field of pattern recognition due to the constraints imposed by variation in the appearance of facial images. These changes in appearance are affected by variation in illumination, expression or occlusions etc. Illumination can be considered a complex problem in both indoor and outdoor pattern matching. Literature studies have revealed that two problems of textural based illumination handling in face recognition seem to be very common. Firstly, textural values are changed during illumination normalization due to increase in the contrast that changes the original pixels of face. Secondly, it minimizes the distance between interclasses which increases the false acceptance rates. This paper addresses these issues and proposes a robust algorithm that overcomes these limitations. The limitations are resolved through transforming pixels from nonillumination side to illuminated side. It has been revealed that proposed algorithm produced better results as compared to existing related algorithms.
TURKISH JOURNAL OF ELECTRICAL ENGINEERING & COMPUTER SCIENCES, 2014
Most face recognition methods are based on linear and nonlinear subspace features extraction and ... more Most face recognition methods are based on linear and nonlinear subspace features extraction and classification tasks. These classification methods are used for global and local facial features for person identification. Both local and global features play different roles for recognition and classification. There are a number of face recognition methods that have been proposed up until now, and they produce good results. However, when small sample size (3S) and pose variation problems are taken into consideration, face recognition becomes more complex and does not produce good results. In this paper, 3S and pose variation problems are dealt with. First, linear discriminate analysis (LDA) is considered to minimize the singularity problem that arises when small samples of individuals are available. In the next step, the proposed framework utilizes global and local facial features and constructs a combined subspace using an enhanced LDA method that is discussed later in the sections.
In this paper a new method of microscopic feature extraction on image processing has been propose... more In this paper a new method of microscopic feature extraction on image processing has been proposed. The proposed technique is effective in extracting desired microscopic features from an image. In this technique dynamic threshold technique is applied on the image in order to remove the background, then vector median filter is applied to remove the noisy pixels for achieving clear image, and finally by digital morphological algorithm to find the desired location in an image is obtained.
In this paper, a face recognition technique "Sub-Holistic Hidden Markov Model" has been proposed.... more In this paper, a face recognition technique "Sub-Holistic Hidden Markov Model" has been proposed. The technique divides the face image into three logical portions. The proposed technique, which is based on Hidden Markov Model (HMM), is then applied to these portions. The recognition process involves three steps i.e. pre-processing, template extraction and recognition. The experiments were conducted on images with different resolutions of the two standard databases (YALE and ORL) and the results were analyzed on the basis of recognition time and accuracy. The accuracy of proposed technique is also compared with SHPCA algorithm, which shows better recognition rates.
A new method is proposed for fast computation of accurate pseudo-Zernike moments for binary and g... more A new method is proposed for fast computation of accurate pseudo-Zernike moments for binary and gray level images. These orthogonal moments are computed as a linear combination of accurate geometric and radial geometric moments, which are computed by mathematical integration of the monomial polynomials over digital image pixels. The proposed method is fast, accurate, simple, and easy programmable. A comparison with the existing methods is performed. The obtained results explain the efficiency of the proposed method.
NGN core flexibility, its subject to adoption and the rapid growth in the personal mobile devices... more NGN core flexibility, its subject to adoption and the rapid growth in the personal mobile devices led to rapid growth in mobile based services as mobile E-Learning. The personalized E-Learning service is proposed based on J2ME , it is integrated with open source IMS control frame work for user management, session establishment using SIP protocol and Multimedia learning content delivery like voice, video, whiteboard sharing using RTP and RTSP. The proposed E-Learning platform comprises on four layers user agent layer (3G mobile phone, J2ME based SIP learning and teaching agent application software), access layer (3G UMTS, Wi-Fi, GPRS), Data communication layer (SIP signaling, XML data exchange between mobile client and Application server) and E-Control and Management layer (IMS control functions, HSS, Learning content application servers). This personalized E-Learning provides opportunity for learners and teachers to learn, teach and control management everywhere.
International Arab Journal of Information Technology, 2013
Automatic Face Recognition is one of the most emphasizing dilemmas in diverse of potential releva... more Automatic Face Recognition is one of the most emphasizing dilemmas in diverse of potential relevance like in different surveillance systems, security systems, authentication or verification of individual like criminals etc. Adjoining of dynamic expression in face causes a broad range of discrepancies in recognition systems. Facial Expression not only exposes the sensation or passion of any person but can also be used to judge his/her mental views and psychosomatic aspects. This paper is based on a complete survey of face recognition conducted under varying facial expressions. In order to analyze different techniques, motion-based, model-based and muscles-based approaches have been used in order to handle the facial expression and recognition catastrophe. The analysis has been completed by evaluating various existing algorithms while comparing their results in general. It also expands the scope for other researchers for answering the question of effectively dealing with such problems.
Detection of textual data from scene text images is a very thoughtprovoking issue in the field of... more Detection of textual data from scene text images is a very thoughtprovoking issue in the field of computer graphics and visualization. This challenge is even more complicated when edge intelligent devices are involved in the process. The low-quality image having challenges such as blur, low resolution, and contrast make it more difficult for text detection and classification. Therefore, such exigent aspect is considered in the study. The technology proposed is comprised of three main contributions. (a) After synthetic blurring, the blurred image is preprocessed, and then the deblurring process is applied to recover the image. (b) Subsequently, the standard maximal stable extreme regions (MSER) technique is applied to localize and detect text. Soon after, K-Means is applied to get three different clusters of the query image to separate foreground and background and also incorporate character level grouping. (c) Finally, the segmented text is classified into textual and non-textual regions using a novel convolutional neural network (CNN) framework. The purpose of this task is to overcome the false positives. For evaluation of proposed technique, results are obtained on three mainstream datasets, including SVT, IIIT5K and ICDAR 2003. The achieved classification results of 90.3% for SVT dataset, 95.8% for IIIT5K dataset, and 94.0% for the ICDAR 2003 dataset, respectively. It shows the preeminence of the proposed methodology that it works fine for good model learning. Finally, the proposed methodology is compared with previous benchmark text-detection techniques to validate its contribution.
Cancer is one of the leading significant causes of illness and chronic disease worldwide. Skin ca... more Cancer is one of the leading significant causes of illness and chronic disease worldwide. Skin cancer, particularly melanoma, is becoming a severe health problem due to its rising prevalence. The considerable death rate linked with melanoma requires early detection to receive immediate and successful treatment. Lesion detection and classification are more challenging due to many forms of artifacts such as hairs, noise, and irregularity of lesion shape, color, irrelevant features, and textures. In this work, we proposed a deep-learning architecture for classifying multiclass skin cancer and melanoma detection. The proposed architecture consists of four core steps: image preprocessing, feature extraction and fusion, feature selection, and classification. A novel contrast enhancement technique is proposed based on the image luminance information. After that, two pre-trained deep models, DarkNet-53 and DensNet-201, are modified in terms of a residual block at the end and trained through...
Research Journal of Applied Sciences, Engineering and Technology
Requirement elicitation is very difficult process in highly challenging and business based softwa... more Requirement elicitation is very difficult process in highly challenging and business based software as well as in real time software. Common problems associated with these types of software are rapidly changing the requirements and understanding the language of the layman person. In this study, a framework for requirement elicitation by using knowledge based system is proposed, which is very helpful for knowledge documentation, intelligent decision support, self-learning and more specifically it is very helpful for case based reasoning and explanation. Basically in this method requirements are gathered from Artificial Intelligence (AI) expert system from various sources e.g., via interviews, scenarios or use cases. Then, these are converted into structured natural language using ontology and this new problem/case is put forward to Case Based Reasoning (CBR). CBR based on its previous information having similar requirements combines with new case and suggests a proposed solution. Based on this solution a prototype is developed and delivered to customer. The use of case-based reasoning in requirements elicitation process has greatly reduced the burden and saved time of requirement analyst and results in an effective solution for handling complex or vague requirements during the elicitation process.
Tumor detection has been an active research topic in recent years due to the high mortality rate.... more Tumor detection has been an active research topic in recent years due to the high mortality rate. Computer vision (CV) and image processing techniques have recently become popular for detecting tumors in MRI images. The automated detection process is simpler and takes less time than manual processing. In addition, the difference in the expanding shape of brain tumor tissues complicates and complicates tumor detection for clinicians. We proposed a new framework for tumor detection as well as tumor classification into relevant categories in this paper. For tumor segmentation, the proposed framework employs the Particle Swarm Optimization (PSO) algorithm, and for classification, the convolutional neural network (CNN) algorithm. Popular preprocessing techniques such as noise removal, image sharpening, and skull stripping are used at the start of the segmentation process. Then, PSO-based segmentation is applied. In the classification step, two pre-trained CNN models, alexnet and inception-V3, are used and trained using transfer learning. Using a serial approach, features are extracted from both trained models and fused features for final classification. For classification, a variety of machine learning classifiers are used. Average dice values on datasets BRATS-2018 and BRATS-2017 are 98.11 percent and 98.25 percent, respectively, whereas average jaccard values are 96.30 percent and 96.57% (Segmentation Results). The results were extended on the same datasets for classification and achieved 99.0% accuracy, sensitivity of 0.99, specificity of 0.99, and precision of 0.99. Finally, the proposed method is compared to state-of-the-art existing methods and outperforms them.
Industry 4.0 smart manufacturing systems are equipped with sensors, smart machines, and intellige... more Industry 4.0 smart manufacturing systems are equipped with sensors, smart machines, and intelligent robots. The automated in-plant transportation of manufacturing parts through throwing and catching robots is an attempt to accelerate the transportation process and increase productivity by the optimized utilization of in-plant facilities. Such an approach requires intelligent tracking and prediction of the final 3D catching position of thrown objects, while observing their initial flight trajectory in real-time, by catching robot in order to grasp them accurately. Due to non-deterministic nature of such mechanically thrown objects’ flight, accurate prediction of their complete trajectory is only possible if we accurately observe initial trajectory as well as intelligently predict remaining trajectory. The thrown objects in industry can be of any shape but detecting and accurately predicting interception positions of any shape object is an extremely challenging problem that needs to b...
Due to the high demand for mango and being the king of all fruits, it is the need of the hour to ... more Due to the high demand for mango and being the king of all fruits, it is the need of the hour to curb its diseases to fetch high returns. Automatic leaf disease segmentation and identification are still a challenge due to variations in symptoms. Accurate segmentation of the disease is the key prerequisite for any computer-aided system to recognize the diseases, i.e., Anthracnose, apicalnecrosis, etc., of a mango plant leaf. To solve this issue, we proposed a CNN based Fully-convolutional-network (FrCNnet) model for the segmentation of the diseased part of the mango leaf. The proposed FrCNnet directly learns the features of each pixel of the input data after applying some preprocessing techniques. We evaluated the proposed FrCNnet on the real-time dataset provided by the mango research institute, Multan, Pakistan. To evaluate the proposed model results, we compared the segmentation performance with the available state-of-the-art models, i.e., Vgg16, Vgg-19, and Unet. Furthermore, the proposed model's segmentation accuracy is 99.2% with a false negative rate (FNR) of 0.8%, which is much higher than the other models. We have concluded that by using a FrCNnet, the input image could learn better features that are more prominent and much specific, resulting in an improved and better segmentation performance and diseases' identification. Accordingly, an automated approach helps pathologists and mango growers detect and identify those diseases.
Mango fruit is in high demand. So, the timely control of mango plant diseases is necessary to gai... more Mango fruit is in high demand. So, the timely control of mango plant diseases is necessary to gain high returns. Automated recognition of mango plant leaf diseases is still a challenge as manual disease detection is not a feasible choice in this computerized era due to its high cost and the non-availability of mango experts and the variations in the symptoms. Amongst all the challenges, the segmentation of diseased parts is a big issue, being the pre-requisite for correct recognition and identification. For this purpose, a novel segmentation approach is proposed in this study to segment the diseased part by considering the vein pattern of the leaf. This leaf vein-seg approach segments the vein pattern of the leaf. Afterward, features are extracted and fused using canonical correlation analysis (CCA)-based fusion. As a final identification step, a cubic support vector machine (SVM) is implemented to validate the results. The highest accuracy achieved by this proposed model is 95.5%, ...
White blood cells, WBCs for short, are an essential component of the human immune system. These c... more White blood cells, WBCs for short, are an essential component of the human immune system. These cells are our body's first line of defense against infections and diseases caused by bacteria, viruses, and fungi, as well as abnormal and external substances that may enter the bloodstream. A wrong WBC count can signify dangerous viral infections, autoimmune disorders, cancer, sarcoidosis, aplastic anemia, leukemia, tuberculosis, etc. A lot of these diseases and disorders can be extremely painful and often result in death. Leukemia is among the more common types of blood cancer and when left undetected leads to death. An early diagnosis is necessary which is possible by looking at the shapes and determining the numbers of young and immature WBCs to see if they are normal or not. Performing this task manually is a cumbersome, expensive, and time-consuming process for hematologists, and therefore computer-aided systems have been developed to help with this problem. This paper proposes ...
Due to the rapid growth in artificial intelligence (AI) and deep learning (DL) approaches, the se... more Due to the rapid growth in artificial intelligence (AI) and deep learning (DL) approaches, the security and robustness of the deployed algorithms need to be guaranteed. The security susceptibility of the DL algorithms to adversarial examples has been widely acknowledged. The artificially created examples will lead to different instances negatively identified by the DL models that are humanly considered benign. Practical application in actual physical scenarios with adversarial threats shows their features. Thus, adversarial attacks and defense, including machine learning and its reliability, have drawn growing interest and, in recent years, has been a hot topic of research. We introduce a framework that provides a defensive model against the adversarial speckle-noise attack, the adversarial training, and a feature fusion strategy, which preserves the classification with correct labelling. We evaluate and analyze the adversarial attacks and defenses on the retinal fundus images for t...
Documents are stored in a digital form across several organizations. Printing this amount of data... more Documents are stored in a digital form across several organizations. Printing this amount of data and placing it into folders instead of storing digitally is against the practical, economical, and ecological perspective. An efficient way of retrieving data from digitally stored documents is also required. This article presents a real-time supervised learning technique for document classification based on deep convolutional neural network (DCNN), which aims to reduce the impact of adverse document image issues such as signatures, marks, logo, and handwritten notes. The proposed technique’s major steps include data augmentation, feature extraction using pre-trained neural network models, feature fusion, and feature selection. We propose a novel data augmentation technique, which normalizes the imbalanced dataset using the secondary dataset RVL-CDIP. The DCNN features are extracted using the VGG19 and AlexNet networks. The extracted features are fused, and the fused feature vector is o...
Provocative heart disease is related to ventricular arrhythmias (VA). Ventricular tachyarrhythmia... more Provocative heart disease is related to ventricular arrhythmias (VA). Ventricular tachyarrhythmia is an irregular and fast heart rhythm that emerges from inappropriate electrical impulses in the ventricles of the heart. Different types of arrhythmias are associated with different patterns, which can be identified. An electrocardiogram (ECG) is the major analytical tool used to interpret and record ECG signals. ECG signals are nonlinear and difficult to interpret and analyze. We propose a new deep learning approach for the detection of VA. Initially, the ECG signals are transformed into images that have not been done before. Later, these images are normalized and utilized to train the AlexNet, VGG-16 and Inception-v3 deep learning models. Transfer learning is performed to train a model and extract the deep features from different output layers. After that, the features are fused by a concatenation approach, and the best features are selected using a heuristic entropy calculation appr...
As the number of internet users increases so does the number of malicious attacks using malware. ... more As the number of internet users increases so does the number of malicious attacks using malware. The detection of malicious code is becoming critical, and the existing approaches need to be improved. Here, we propose a feature fusion method to combine the features extracted from pre-trained AlexNet and Inception-v3 deep neural networks with features attained using segmentation-based fractal texture analysis (SFTA) of images representing the malware code. In this work, we use distinctive pre-trained models (AlexNet and Inception-V3) for feature extraction. The purpose of deep convolutional neural network (CNN) feature extraction from two models is to improve the malware classifier accuracy, because both models have characteristics and qualities to extract different features. This technique produces a fusion of features to build a multimodal representation of malicious code that can be used to classify the grayscale images, separating the malware into 25 malware classes. The features ...
Feature transformation and key-point identification is the solution to many local feature descrip... more Feature transformation and key-point identification is the solution to many local feature descriptors. One among such descriptor is the Scale Invariant Feature Transform (SIFT). A small effort has been made for designing a hexagonal sampled SIFT feature descriptor with its applicability in face recognition tasks. Instead of using SIFT on square image coordinates, the proposed work makes use of hexagonal converted image pixels and processing is applied on hexagonal coordinate system. The reason of using the hexagonal image coordinates is that it gives sharp edge response and highlights low contrast regions on the face. This characteristic allows SIFT descriptor to mark distinctive facial features, which were previously discarded by original SIFT descriptor. Furthermore, Fisher Canonical Correlation Analysis based discriminate procedure is outlined to give a more precise classification results. Experiments performed on renowned datasets revealed better performances in terms of feature extraction in robust conditions.
Face recognition is one of a complex biometrics in the field of pattern recognition due to the co... more Face recognition is one of a complex biometrics in the field of pattern recognition due to the constraints imposed by variation in the appearance of facial images. These changes in appearance are affected by variation in illumination, expression or occlusions etc. Illumination can be considered a complex problem in both indoor and outdoor pattern matching. Literature studies have revealed that two problems of textural based illumination handling in face recognition seem to be very common. Firstly, textural values are changed during illumination normalization due to increase in the contrast that changes the original pixels of face. Secondly, it minimizes the distance between interclasses which increases the false acceptance rates. This paper addresses these issues and proposes a robust algorithm that overcomes these limitations. The limitations are resolved through transforming pixels from nonillumination side to illuminated side. It has been revealed that proposed algorithm produced better results as compared to existing related algorithms.
TURKISH JOURNAL OF ELECTRICAL ENGINEERING & COMPUTER SCIENCES, 2014
Most face recognition methods are based on linear and nonlinear subspace features extraction and ... more Most face recognition methods are based on linear and nonlinear subspace features extraction and classification tasks. These classification methods are used for global and local facial features for person identification. Both local and global features play different roles for recognition and classification. There are a number of face recognition methods that have been proposed up until now, and they produce good results. However, when small sample size (3S) and pose variation problems are taken into consideration, face recognition becomes more complex and does not produce good results. In this paper, 3S and pose variation problems are dealt with. First, linear discriminate analysis (LDA) is considered to minimize the singularity problem that arises when small samples of individuals are available. In the next step, the proposed framework utilizes global and local facial features and constructs a combined subspace using an enhanced LDA method that is discussed later in the sections.
In this paper a new method of microscopic feature extraction on image processing has been propose... more In this paper a new method of microscopic feature extraction on image processing has been proposed. The proposed technique is effective in extracting desired microscopic features from an image. In this technique dynamic threshold technique is applied on the image in order to remove the background, then vector median filter is applied to remove the noisy pixels for achieving clear image, and finally by digital morphological algorithm to find the desired location in an image is obtained.
In this paper, a face recognition technique "Sub-Holistic Hidden Markov Model" has been proposed.... more In this paper, a face recognition technique "Sub-Holistic Hidden Markov Model" has been proposed. The technique divides the face image into three logical portions. The proposed technique, which is based on Hidden Markov Model (HMM), is then applied to these portions. The recognition process involves three steps i.e. pre-processing, template extraction and recognition. The experiments were conducted on images with different resolutions of the two standard databases (YALE and ORL) and the results were analyzed on the basis of recognition time and accuracy. The accuracy of proposed technique is also compared with SHPCA algorithm, which shows better recognition rates.
A new method is proposed for fast computation of accurate pseudo-Zernike moments for binary and g... more A new method is proposed for fast computation of accurate pseudo-Zernike moments for binary and gray level images. These orthogonal moments are computed as a linear combination of accurate geometric and radial geometric moments, which are computed by mathematical integration of the monomial polynomials over digital image pixels. The proposed method is fast, accurate, simple, and easy programmable. A comparison with the existing methods is performed. The obtained results explain the efficiency of the proposed method.
NGN core flexibility, its subject to adoption and the rapid growth in the personal mobile devices... more NGN core flexibility, its subject to adoption and the rapid growth in the personal mobile devices led to rapid growth in mobile based services as mobile E-Learning. The personalized E-Learning service is proposed based on J2ME , it is integrated with open source IMS control frame work for user management, session establishment using SIP protocol and Multimedia learning content delivery like voice, video, whiteboard sharing using RTP and RTSP. The proposed E-Learning platform comprises on four layers user agent layer (3G mobile phone, J2ME based SIP learning and teaching agent application software), access layer (3G UMTS, Wi-Fi, GPRS), Data communication layer (SIP signaling, XML data exchange between mobile client and Application server) and E-Control and Management layer (IMS control functions, HSS, Learning content application servers). This personalized E-Learning provides opportunity for learners and teachers to learn, teach and control management everywhere.
International Arab Journal of Information Technology, 2013
Automatic Face Recognition is one of the most emphasizing dilemmas in diverse of potential releva... more Automatic Face Recognition is one of the most emphasizing dilemmas in diverse of potential relevance like in different surveillance systems, security systems, authentication or verification of individual like criminals etc. Adjoining of dynamic expression in face causes a broad range of discrepancies in recognition systems. Facial Expression not only exposes the sensation or passion of any person but can also be used to judge his/her mental views and psychosomatic aspects. This paper is based on a complete survey of face recognition conducted under varying facial expressions. In order to analyze different techniques, motion-based, model-based and muscles-based approaches have been used in order to handle the facial expression and recognition catastrophe. The analysis has been completed by evaluating various existing algorithms while comparing their results in general. It also expands the scope for other researchers for answering the question of effectively dealing with such problems.
Detection of textual data from scene text images is a very thoughtprovoking issue in the field of... more Detection of textual data from scene text images is a very thoughtprovoking issue in the field of computer graphics and visualization. This challenge is even more complicated when edge intelligent devices are involved in the process. The low-quality image having challenges such as blur, low resolution, and contrast make it more difficult for text detection and classification. Therefore, such exigent aspect is considered in the study. The technology proposed is comprised of three main contributions. (a) After synthetic blurring, the blurred image is preprocessed, and then the deblurring process is applied to recover the image. (b) Subsequently, the standard maximal stable extreme regions (MSER) technique is applied to localize and detect text. Soon after, K-Means is applied to get three different clusters of the query image to separate foreground and background and also incorporate character level grouping. (c) Finally, the segmented text is classified into textual and non-textual regions using a novel convolutional neural network (CNN) framework. The purpose of this task is to overcome the false positives. For evaluation of proposed technique, results are obtained on three mainstream datasets, including SVT, IIIT5K and ICDAR 2003. The achieved classification results of 90.3% for SVT dataset, 95.8% for IIIT5K dataset, and 94.0% for the ICDAR 2003 dataset, respectively. It shows the preeminence of the proposed methodology that it works fine for good model learning. Finally, the proposed methodology is compared with previous benchmark text-detection techniques to validate its contribution.
Uploads
Papers by Dr. Jamal Shah